发明名称 |
METHODS AND APPARATUS FOR ENTITY DETECTION |
摘要 |
Techniques for entity detection include matching a token from at least a portion of a text string with a matching concept in an ontology, wherein the at least a portion of the text string has been labeled as corresponding to a particular entity type. A first concept may be identified as being hierarchically related to the matching concept within the ontology, and a second concept may be identified as being hierarchically related to the first concept within the ontology. Based at least in part on the labeling of the at least a portion of the text string as corresponding to the particular entity type, a statistical model may be trained to associate the first concept with a first probability of corresponding to the particular entity type and the second concept with a second probability of corresponding to the particular entity type. |
申请公布号 |
US2014279729(A1) |
申请公布日期 |
2014.09.18 |
申请号 |
US201313796101 |
申请日期 |
2013.03.12 |
申请人 |
Nuance Communications, Inc. |
发明人 |
Delaney Brian W.;Yegnanarayanan Girija |
分类号 |
G06N99/00 |
主分类号 |
G06N99/00 |
代理机构 |
|
代理人 |
|
主权项 |
1. A method comprising:
matching a token from at least a portion of a text string with a matching concept in an ontology, wherein the at least a portion of the text string has been labeled as corresponding to a particular entity type; identifying a first concept as being hierarchically related to the matching concept within the ontology; identifying a second concept as being hierarchically related to the first concept within the ontology; and training, using at least one processor, a statistical model to associate the first concept with a first probability of corresponding to the particular entity type and the second concept with a second probability of corresponding to the particular entity type, based at least in part on the labeling of the at least a portion of the text string as corresponding to the particular entity type. |
地址 |
Burlington MA US |